graphify
Fail
Audited by Snyk on Aug 28, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the LLM to ask the user for Neo4j credentials (
NEO4J_USER,NEO4J_PASSWORD) and then pass them directly into a Python command argument string (password='NEO4J_PASSWORD'), which results in handling secret values directly in the LLM context and generated commands.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow processes local files and ingested URLs, and includes an
add <url>feature that fetches arbitrary external web pages and documents into the corpus.
Issues (2)
W007
HIGHInsecure credential handling detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata